Pans Github Scout

• Outcome: Pass
• Latest audit: May 29, 2026, 8:40 PM
• Version:
  1.0.0

Overview

This skill appears to be a user-run GitHub lead search/export tool with no hidden installation, persistence, or destructive behavior.

Before installing, treat exported lead files as potentially sensitive business/contact data. Use enrichment and CSV export only for appropriate lawful purposes, store exports carefully, and avoid giving the tool a broad GitHub token.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The skill advertises executable behavior that implies network access, environment access, and file writing, but it does not declare any permissions or constraints. This creates a trust gap: operators cannot accurately assess what the skill may access or modify, and hidden capability expansion is a common path to unintended data exposure or unauthorized outbound requests.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 82% confidence
• Finding: The skill description promises narrowly scoped lead discovery for AI companies with specific filters, but the described behavior is broader and some claimed filters are not implemented. Description-behavior mismatch is dangerous because users may authorize or trust the skill under false assumptions, leading to over-collection, misuse outside intended scope, or unreliable business decisions from incomplete filtering.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The script writes collected lead data, including organization email and location fields, directly to CSV on disk without any consent prompt, field minimization, or sensitivity warning. In a lead-generation context, this increases the risk of unintended retention, redistribution, or mishandling of contact information, especially if exports are stored insecurely or shared broadly.

VirusTotal

65/65 vendors flagged this skill as clean.